Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 77 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0252. Min Range: -3.0252
Max Act: 3.0252. Min Act: -0.1700
Data Index: 1316952 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0252. Min Range: -3.0252
Max Act: 3.0094. Min Act: -0.1700
Data Index: 563205 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.9778. Min Act: -0.1700
Data Index: 656001 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.9461. Min Act: -0.1700
Data Index: 40716 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.9303. Min Act: -0.1700
Data Index: 892529 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.9303. Min Act: -0.1700
Data Index: 17324 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8986. Min Act: -0.1700
Data Index: 1180666 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.9303. Min Act: -0.1700
Data Index: 1147946 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.9303. Min Act: -0.1700
Data Index: 1348643 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8827. Min Act: -0.1700
Data Index: 1108668 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8986. Min Act: -0.1700
Data Index: 40372 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8986. Min Act: -0.1700
Data Index: 789944 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8827. Min Act: -0.1700
Data Index: 1413396 (Python Code)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8986. Min Act: -0.1700
Data Index: 1350551 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8827. Min Act: -0.1700
Data Index: 1032268 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8827. Min Act: -0.1700
Data Index: 713178 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8827. Min Act: -0.1700
Data Index: 545854 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8827. Min Act: -0.1700
Data Index: 937349 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8668. Min Act: -0.1700
Data Index: 1203066 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0252. Min Range: -3.0252
Max Act: 2.8510. Min Act: -0.1700
Data Index: 955720 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19